KR101584887B1 - Method and system of supporting multitasking of speech recognition service in in communication device - Google Patents

Abstract

Embodiments of the present invention relate to a method and system for supporting multitasking of speech recognition services. A method of supporting multitasking of a speech recognition application in a communication terminal, the method comprising: operating a speech recognition application in an execution standby mode with operation of a first application; Receiving a predetermined awake up command of the speech recognition application and operating the speech recognition application in an execution mode; Transmitting voice data recorded by a user through voice recognition application to a server; And receiving the execution result corresponding to the recorded data from the server and operating the communication terminal. [0031] According to another aspect of the present invention, there is provided a method for supporting multitasking of a voice recognition application in a communication terminal.

Description

TECHNICAL FIELD [0001] The present invention relates to a method and system for supporting multitasking of a voice recognition service in a communication terminal,

An embodiment of the present invention relates to a method of providing a voice recognition service supporting multitasking and a communication terminal providing the service.

Electronic devices such as mobile phones and tablet PCs are becoming popular with the recent development of digital technology. Such electronic devices are used for voice communication, video call, message transmission and reception, video reproduction, Internet, electronic commerce music reproduction, social network service (SNS) And so on.

Digital technology has been developed to enable users of electronic devices to use them more conveniently, and the accuracy and convenience of speech recognition services are increasing day by day.

We are introducing voice recognition technology into electronic devices, and major IT companies around the world are applying voice recognition technology to core products and services.

Previous speech recognition techniques have been difficult to use for controlling communication devices due to low recognition rate, but the speech recognition rate has been greatly improved due to the continuous development of related technologies. Accordingly, it is possible to operate the communication terminal without physical manipulation of the user's communication terminal by using the voice recognition, and inputting information through voice during movement and work is becoming easier.

Existing speech recognition applications installed in the terminal for recognizing a voice input from a user do not support multitasking. Therefore, in order to operate the communication terminal through the voice recognition application, the currently running application has to be terminated and the voice recognition application has to be newly activated. Due to this problem, it has not been possible to operate the communication terminal through voice recognition while using other applications such as games or reading.

In an embodiment of the present invention, a problem that multitasking of a voice recognition application is not provided in a communication terminal is solved, and a voice recognition service can be provided through a voice recognition application even while another application is operating.

A method of supporting multitasking of a speech recognition application in a communication terminal, the method comprising: operating a speech recognition application in an execution standby mode with operation of a first application; Receiving a predetermined awake up command of the speech recognition application and operating the speech recognition application in an execution mode; Transmitting voice data recorded by a user through voice recognition application to a server; And receiving the execution result corresponding to the recorded data from the server and operating the communication terminal. [0031] According to another aspect of the present invention, there is provided a method for supporting multitasking of a voice recognition application in a communication terminal.

The step of operating the voice recognition application in the execution standby mode together with the operation of the first application may include displaying the first application on the uppermost layer of the display of the communication terminal, ; And operating the speech recognition application in a standby mode at a back-ground.

In another aspect of the present invention, the step of operating the voice recognition application in the execution mode by receiving a predetermined awake up command of the voice recognition application may include receiving an awake up command of the voice recognition application step; Determining whether a wake-up command of the speech recognition application corresponds to a wake-up command of the predetermined speech recognition application; And operating the speech recognition application in an execution mode when it is determined that the awake up command of the speech recognition application corresponds to a wake up command of a predetermined speech recognition application.

In another aspect of the present invention, the step of operating the voice recognition application in the execution mode may include the steps of maintaining the operation of the first application such that the first application is displayed on the uppermost layer of the display of the communication terminal, and operating the speech recognition application in an execution mode at a back-ground.

In yet another aspect, the predetermined awake up command of the speech recognition application may be a predetermined speech recognition application execution command for executing the speech recognition application.

In yet another aspect, the predetermined awake up command of the speech recognition application may include at least one of a voice received from a user or a call reception, a character reception, and a messenger reception in an execution standby mode of the voice recognition application Lt; / RTI >

According to another aspect of the present invention, the step of transmitting the recorded voice data recorded by the voice recognition application to the server may include transmitting the address book data stored in the communication terminal to the server together.

In another aspect, the step of receiving an execution result corresponding to the recorded data from the server and operating the communication terminal may include executing at least one of a phone call, a phone call, a message transmission, a message reception, or a messenger reception .

In another aspect, the method may further include displaying a message corresponding to the call origination, the call reception, the message origination, the message reception, or the messenger reception operation on a window associated with the voice recognition application.

In another aspect, the step of displaying a message corresponding to the call origination, call reception, message origination, message reception, or messenger reception operation on a window associated with the voice recognition application comprises: And overlapping the first application with a translucent display on the display of the communication terminal.

According to another aspect of the present invention, the step of overlapping and displaying a window associated with the hands-free application in a translucent manner with respect to the first application may include the step of displaying the size of the window as text data corresponding to the voice data And adjusting and displaying the information according to the length.

According to another aspect of the present invention, the step of receiving an execution result corresponding to the recording data from the server and operating the communication terminal comprises: measuring an ambient noise level of the communication terminal; Comparing the ambient noise magnitude and the speaker volume magnitude of the communication terminal; And adaptively adjusting the speaker volume size based on the ambient noise magnitude.

According to another aspect of the present invention, the step of receiving an execution result corresponding to the recording data from the server and operating the communication terminal includes adaptively adjusting an output volume size of the voice recognition application and the first application .

It is possible to solve the problem that multitasking of the voice recognition application is not provided in the communication terminal and to provide the voice recognition service through the voice recognition application while another application is operating.

FIG. 1 is a flowchart illustrating a method of supporting multitasking of a speech recognition service according to an exemplary embodiment of the present invention. Referring to FIG.
2 is a view for explaining an example in which a voice recognition service supporting multitasking is provided according to an embodiment of the present invention.
3 is a diagram for explaining an example in which a voice recognition service supporting multitasking is provided according to an embodiment of the present invention.
4 is a diagram for explaining a method of providing a text window among voice recognition services supporting multitasking according to an embodiment of the present invention.

Hereinafter, a method of supporting multitasking of a voice recognition service in a communication terminal will be described in detail with reference to the accompanying drawings.

As described above, the present invention is intended to provide multitasking in order to provide a voice recognition service so that a user can use voice recognition service at any time in various situations using the terminal.

<Scenario that operates according to user's start command voice>

FIG. 1 is a flowchart illustrating a method of supporting multitasking of a speech recognition service according to an exemplary embodiment of the present invention. Referring to FIG.

In step 110, the voice recognition application may be operated in the standby mode together with the operation of the first application. Here, the first application is for an application other than the voice recognition application in the terminal, and the operation of the first application may correspond to, for example, a state in which a game, a moving picture, or a document is being created.

In the embodiment, operating the speech recognition application in the execution standby mode means waiting for an instruction to execute the speech recognition application that provides the speech recognition service.

When the first application is operated, the first application is operated while being displayed on the uppermost layer of the display of the communication terminal, and the speech recognition application is executed in the background (back-ground) independently of the operation of the first application Mode. In an embodiment, the voice recognition application may operate in a standby mode regardless of whether the first application is operating or not.

The step 110 according to the embodiment may include not only the operation state of the first application but also a state where the screen of the communication terminal is turned off, a state where the communication terminal is locked off, ) State, a state in which the communication terminal has received a voice call, and a state in which the communication terminal has received a text message, or the like.

In step 120, a predetermined awake up command of the speech recognition application may be received to operate the speech recognition application in the execution mode.

In an embodiment, when the speech recognition application operates in an execution mode, the operation of the first application may remain as it is displayed in the top layer of the display of the communication terminal, and the speech recognition application may provide multicasting .

For this purpose, a voice for a wake-up command can be received from a user through input means such as a microphone of a communication terminal. The communication terminal can confirm whether or not the voice input from the user corresponds to a predetermined wake-up command. In an embodiment, the predefined wakeup command may be a voice with a short text, for example " lower ". The "correspondence" means not only the case where two voices are completely equal but also the case where two voices can be judged to be substantially the same voice within a predetermined error range in a comparative analysis.

As a result of the determination, when the voice of the user received in the communication terminal corresponds to a predetermined wake-up command, the voice recognition application according to the embodiment of the present invention can be operated in the execution mode.

The speech recognition application may operate in the execution standby mode and operate in the execution mode through the wakeup command input by the user.

In the embodiment, when at least one event such as call reception, text reception, messenger reception, etc. is generated in the communication terminal, the voice recognition application receives the event as a wake up command and executes the voice recognition application in the execution standby mode Mode.

On one side, speech recognition applications operating in the execution mode support multitasking. That is, the communication terminal can provide the voice recognition service to the user through the voice recognition application while continuously surfing the web while watching the moving picture while playing the first application, for example, playing a game.

In an embodiment, the voice recognition application may be operated in a back-ground execution mode while maintaining the operation of the first application so that the first application is displayed on the uppermost layer of the display of the communication terminal.

In the embodiment, the voice recognition application operates in the execution mode and sends a voice input request message such as a microphone icon for receiving voice of a user to a partial area of the display of the communication terminal or 'What can I do?' Can be displayed.

In step 130, the user can transfer the recorded voice data of the user through the voice recognition application to the server.

According to one aspect, the voice data may correspond to voice input from the user through the microphone of the communication terminal. The speech recognition application can receive voice data from a user and record the received voice data to generate voice data.

The voice data received from the user may be voice including call reception, text / IM message reception and transmission, or execution instruction of the first application. The recording data may be transmitted to a server. At this time, the recorded data can be transmitted to the server through the wired / wireless network connected to the communication terminal.

In step 130, when the communication terminal transmits the recording data corresponding to the voice input from the user to the server, the communication terminal may transmit the address book data or the call recording information stored in the communication terminal together with the recording data to the server. According to another aspect, the address book data or call record information may be transmitted to the server separately from the recorded data.

In this case, the server can process the text data using the address book data or call record information transmitted together with the recording data. For example, when voice data for call and message transmission is input, the address book data may be transmitted to the server together with the recording data so that the server can search for a destination of the call and message transmission.

In step 140, the execution result corresponding to the recorded data can be received from the server to operate the communication terminal.

The server uses STT (Speech to text ) technology to convert the recorded data into text data. When the server generates the text data from the recording data, the recording data is analyzed to extract the characteristics of the user voice data included in the recording data and stores it as a log value, so that when the user voice data is recognized Can be used. The server can delete the recorded data converted into text data.

The communication terminal can receive the text file transmitted from the server. The speech recognition application can receive the text data transmitted from the server as a result of execution on the recorded data. The application can operate the communication terminal according to the received text data. Accordingly, the operation of the communication terminal may be any one of telephone call, text creation and transmission, and execution of another application.

Various variant scenarios are described in detail below.

<Modification Scenarios>

According to one aspect of the present invention, the server may include the address data for two or more subjects in the text data when the result of the conversion of the voice data inputted by the user is that two or more persons (same name) are converted into the same text data on the address book data . In this case, the server refers to the call record information, and can sort information on two or more subjects in order of recent call or frequent call, and provide the information to the communication terminal.

According to another aspect of the present invention, the server refers to the call record information when the contact information of the target is two or more (home phone, mobile phone, etc.) on the address book data as a result of conversion of the recorded data, Can be converted. In addition, the server can convert all of the two or more contacts into text data, and the communication terminal can display two or more contacts on the screen in the form of a list.

According to another aspect of the present invention, the server confirms whether there is a missed call in the communication terminal when voice data indicating that the communication terminal confirms the missed call from the user is confirmed as a result of the recording data conversion. The user can make a list up with a voice guidance or send a call automatically to a caller of a missed call with voice guidance.

According to another aspect, the speech recognition application can output the text data received from the server on the screen. In this case, the application measures the length of the text data and adaptively adjusts the size of a bubble-shaped window for displaying the text data on the screen when the text data is output on the screen of the communication terminal . For example, the larger the length of the text data, the larger the size of the window, and the smaller the size of the window, the smaller the size of the text data placed in the window.

According to one aspect of the present invention, the voice recognition application may measure the ambient noise input through the microphone of the communication terminal and may adaptively adjust the volume of the output speaker of the communication terminal according to the measured ambient noise level. At this time, the voice recognition application can compare the numerical value of the ambient noise size and the volume size of the output speaker of the communication terminal. If the comparison result indicates that the ambient noise size is larger than the volume size of the output speaker, Can be adaptively adjusted to be higher than the noise magnitude. As a result of comparison, if the ambient noise size is smaller than the volume size of the output speaker, the speaker volume of the communication terminal can be reduced.

According to one aspect, if the ambient noise magnitude is greater than the predetermined speaker volume limit, the speech recognition application installed in the communication terminal may suspend the speech recognition service.

According to another aspect of the present invention, when an application such as a game or a moving picture is being executed, a problem may arise in which a voice output through a speaker of a communication terminal and a voice output during operation of a voice recognition application are output. Therefore, in the embodiment of the present invention, when the communication terminal is operated according to the execution result, the volume of the output of the first application which was being executed in the communication terminal and the volume of the output of the speech recognition application executed simultaneously with the first application The size of the volume of the output of the first application can be automatically adjusted so that the output volume of the recognition application is higher than a certain level.

<Scenarios in which an operation is started upon receiving a call>

As described above, the voice recognition application can operate in the execution mode when a call is received even if the voice of the user is not inputted. In the embodiment, while the speech recognition application operates in the execution mode, the display of the communication terminal can display the operation of the first application as it is.

And receive voice data from the user to connect the received call. To this end, voice data for inquiring the user about the call connection together with the execution mode operation of the voice recognition application can be outputted through the speaker of the communication terminal.

The following description relates to an embodiment of the present invention performed when a call is received by a communication terminal. In the case where call reception is detected in the communication terminal, the communication terminal can operate in the background or in an execution mode in which the application is not running. A voice recognition service can be provided through an application operating in the execution mode.

When the call reception is detected by the communication terminal, voice data for inquiring the user of the communication terminal as to whether or not the call is connected can be outputted through the speaker. This is to ask the user's opinion on whether to connect the received call.

In an embodiment, when a call reception is detected in the communication terminal, the communication terminal can transmit the calling number (Caller ID, etc.) of the call and the address book data or call log information stored in the communication terminal to the server. The server can generate call reception voice data by referring to the calling number and address book data or call recording information transmitted from the communication terminal. For example, when a call is received from Hong Gil Dong, whose telephone number is 010-111-1111, the communication terminal transmits the telephone number and the address book data or call record information stored in the communication terminal to the server.

The server refers to the corresponding phone number and address book data and confirms that the call is received from Hong Kil-dong, and "A call from Hong Gil-dong is received. Do you want to receive it?" And transmits the generated voice data to the communication terminal.

The name of the caller corresponding to the calling number of the call is retrieved from the address book data stored in the communication terminal and the voice data corresponding to the name of the searched caller and the announcement voice data combined with the predetermined call reception voice data can be outputted. For example, if the name of the caller is 'Hong Gil Dong', the voice data corresponding to 'Hong Gil Dong' and '~' are called. 'Would you like to connect?', Combined with the voice data received, 'Hong Gil-dong called. Do you want to connect? ' And can announce the call reception to the user.

Thereafter, the communication terminal waits for confirmation input of the voice data from the user. Here, the acknowledgment input may be a positive or negative response to the call connection request.

When the confirmation input is received as voice data from the user, the communication terminal can record the voice and generate the voice data. The communication terminal transmits the generated recording data to the server. The server uses STT (Speech to text ) technology to convert the recorded data into text data. The server can transmit the generated text data to the communication terminal.

Accordingly, the speech recognition application can receive text data as a result of execution on the recorded data. Here, the text data includes texts such as 'Yes', 'Yes', 'Yes', 'Yes', etc. indicating the call connection affirmation, or 'No', 'No', 'No' May be included.

The speech recognition application may recognize the call connection affirmation and the text data regarding the call connection negation and accept or reject the call connection request. In an embodiment, the application may be predefined for each of the text data for call connection affirmation and negation. Therefore, it is possible to connect the received call in case of call connection affirmation, and to leave the call in case of negative call connection or leave it unconnected.

&Lt; Scenario in which an operation is started upon receiving a text message >

Similar to the embodiment for receiving the telephone described above, the communication terminal can operate the speech recognition application in the execution mode based on the reception of the text message. As in the previous embodiment, while the speech recognition application operates in the execution mode, the display of the communication terminal can display the operation of the first application as it is.

The communication terminal can transmit the calling number (Caller ID, etc.) of the text message and the address book data or the call recording information stored in the communication terminal to the server. The server can generate the text message reception voice data by referring to the calling number, address book data or call log information transmitted from the communication terminal. For example, when a text message is received from Hong Gil Dong having a telephone number 010-111-1111, the communication terminal transmits the telephone number and the address book data or call record information stored in the communication terminal to the server.

The server confirms that the text message is received from Hong Kil Dong by referring to the telephone number and the address book data, and the message " And transmits the generated voice data to the communication terminal.

Thereafter, the communication terminal waits for confirmation input of the voice data from the user. Here, the confirmation input may be a response to a positive or negative response to a request for viewing a text message. When the confirmation input is received from the user by voice, the voice can be recorded to generate the recorded data. The communication terminal transmits the generated recording data to the server.

The server can generate text data from the recorded data. The server can convert the recorded data into text data using STT (Speech to text ) technology. The server can transmit the generated text data to the communication terminal. Accordingly, the voice recognition application of the communication terminal can receive the text data transmitted from the server as a result value for the recorded data. Here, the text data includes texts such as 'Yes', 'Yes', 'Yes', 'Yes', etc. indicating the affirmation of reading a text message, or 'No' or 'No'',' No ', and so on.

The voice recognition application of the communication terminal recognizes the text data related to the positive and negative readings of the text message so that the communication terminal can operate according to whether the text data corresponds to a text message read affirmation or a text message read negative.

If the text data received from the server corresponds to an illegal reading of a text message, the communication terminal can return to the standby state without waiting for any operation and wait for another text message reception. On the other hand, in the case of responding to a text message read affirmation, the communication terminal can transmit the text data of the received text message to the server.

The server can generate the voice data from the text data of the text message. The server can convert the text data of a text message into voice data through the STT function, and the server can transmit the generated voice data to the communication terminal again. According to the embodiment, the server performing the STT function may be implemented as a server physically separate from the server performing the TTS function, and may be physically implemented as one server.

The voice recognition application causes the voice data received from the server to be output to the speaker of the communication terminal. The user can easily check the received text message even in a situation where the communication terminal outputs the received text message as voice data and the communication terminal is difficult to operate, such as during operation or during exercise.

<Example of UI of speech recognition application>

Hereinafter, an example in which the speech recognition service of the present invention is provided will be described with reference to FIG. 2 through FIG. The embodiments of FIGS. 2 to 3 may be performed after the voice recognition application operates in the background through a wake-up command.

2 is a view for explaining an example in which a voice recognition service supporting multitasking is provided according to an embodiment of the present invention.

When the communication terminal receives the user's start command voice and confirms whether the voice of the user received at the communication terminal is a predetermined wake up command and if the voice received at the communication terminal is a predetermined wake up command, The speech recognition application according to the embodiment of the present invention can be operated in the execution mode.

At this time, the voice recognition application can operate in the background while keeping the operation so that the first application being executed in the communication terminal is displayed in the uppermost layer of the communication terminal.

In the embodiment, when the speech recognition application is operated in the background in the execution mode, the guidance message 210 for inputting the voice data received from the user is transmitted to a part of the screen of the communication terminal As shown in FIG. At this time, the window may overlap and display a part of the screen of the communication terminal in a state of executing the first application in a translucent manner. The guidance message 210 may be omitted or output as a voice. As shown in FIG. 2, when the guidance message 210 is displayed on a part of the screen, a delete button for deleting the window may be provided.

The voice recognition application of the communication terminal generates a voice that is received from the user as recording data. The communication terminal transmits the recording data to the server. When transmitting the recorded data to the server, the address book data or the call record information stored in the communication terminal can be transmitted to the server together with the recorded data. The address book data or call record information may be transmitted separately from the recorded data.

The server can analyze the recorded data and generate text data for the 'telephone call' included in the recorded data. The server receiving the address book data or the call record information stored in the communication terminal can process the text data by obtaining the information on the caller of the telephone call from the recorded data, the address book data or the call record information. The server transmits the converted text data to the communication terminal. The voice recognition application of the communication terminal can recognize the text data received from the server and perform a telephone call operation.

In another embodiment, the voice recognition application of the communication terminal transmits the recorded voice data recorded with the telephone call voice containing the caller to the server, retrieves the caller included in the text data received from the server from the contact in the communication terminal, The caller can be connected to the call. In another embodiment, an application that receives text data from a server when the sender is not included in the recorded data may launch a dial window on the display of the communication terminal, or may output a message requesting the caller.

The voice recognition application can cause the communication terminal to operate according to the voice data input from the user. 2, the voice recognition application of the communication terminal can perform a 'call to Kim Soo-hyun' to make a call to 'Kim Soo-hyun'. 2, the voice recognition application can display the text data received from the server in a partial area 220 of the communication terminal screen.

FIG. 3 is a diagram similar to FIG. 2 for explaining an example in which a voice recognition service supporting multitasking is provided.

According to the embodiment, the communication terminal receives the start command voice of the user, confirms whether or not the voice received from the user at the communication terminal is a predetermined wake up command, and if the voice received at the communication terminal is a predetermined wake up Command, the speech recognition application according to the embodiment of the present invention can operate in the execution mode. At this time, the voice recognition application can operate in the background of the communication terminal while displaying the operation of the first application on the uppermost layer of the communication terminal.

In the embodiment, the terminal status of FIG. 3 may not output a guidance message, unlike FIG. 2, in a state in which the voice recognition application operates in the background in the execution mode. The user receives the voice data 'Let character read from Kim Doo-Hyun and make a phone call' from the user.

The voice recognition application of the communication terminal generates voice data received from the user as voice data. The communication terminal transmits the recording data to the server. When transmitting the recorded data to the server, the address book data or the call record information stored in the communication terminal can be transmitted to the server together with the recorded data. The address book data or call record information may be transmitted separately from the recorded data.

The server analyzes the recorded data and can generate text data for the 'character reading' and the 'telephone connection' included in the recorded data. The server receiving the address book data or the call log information stored in the communication terminal, The address book data, or the call log information, and the text data may be processed by the server. The server transmits the converted text data to the communication terminal. The text data can be recognized and the voice data output of the text message and the telephone call operation can be performed through interlocking with the server in the above-described manner.

3, the voice recognition application can display the text data received from the server in a partial area 310 of the communication terminal screen

In an embodiment, the communication terminal may receive a termination voice command from a user and verify that the termination voice command entered from the user matches a predetermined termination command voice. If the end voice command input to the communication terminal matches the predetermined end voice command, the running voice recognition application can be terminated. The termination of the speech recognition application may include an operation of one of the applications terminating completely or returning to the sleep mode again. The predetermined ending voice command may correspond to a voice in short text, for example, &quot; Goodbye &quot;.

&Lt; Modification of UI displayed on communication terminal screen >

4 is a diagram for explaining a method of providing a text window among voice recognition services supporting multitasking according to an embodiment of the present invention.

A text window associated with the speech recognition application as shown in FIG. 4 may be provided, the size of the window may be determined according to the length of the text. The text window of FIG. 4 is a text window containing the text data 220 of FIG. 2 and the text data 310 of FIG.

In the embodiment, a text window for the voice data 'Call to Kim Soo Hyun' may be provided. If the voice button 410 is tapped, the smallest size such as the screen 411 May be provided.

In addition, if the text 420 is tapped, a keyboard such as the screen 421 can be provided so that the created text can be modified, and the size of the text window can be adaptively adjusted according to the length or size of the text directly input by the user Lt; / RTI &gt;

According to one aspect of the present invention, the voice recognition application measures the length of the text data when outputting the text data received from the server on the screen, and when the text data is outputted on the screen of the communication terminal, The size of the speech bubble-like window to be displayed can be adaptively adjusted. For example, the larger the length of the text data, the larger the size of the window, and the smaller the size of the window, the smaller the size of the text data placed in the window.

A system supporting multitasking of the speech recognition service as described above can be provided. A system according to an embodiment may be implemented with hardware components, software components, and / or a combination of hardware components and software components. For example, the system and components may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit ), A microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For ease of understanding, the processing apparatus may be described as being used singly, but those skilled in the art will recognize that the processing apparatus may have a plurality of processing elements and / As shown in FIG. For example, the processing unit may comprise a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as a parallel processor.

The software may include a computer program, code, instructions, or a combination of one or more of the foregoing, and may be configured to configure the processing device to operate as desired or to process it collectively or collectively Device can be commanded. The software and / or data may be in the form of any type of machine, component, physical device, virtual equipment, computer storage media, or device , Or may be permanently or temporarily embodied in a transmitted signal wave. The software may be distributed over a networked computer system and stored or executed in a distributed manner. The software and data may be stored on one or more computer readable recording media.

Through the above-described embodiment, a voice recognition application that solves the problem that multitasking is not performed in the terminal by supplementing the voice recognition service that has been provided, and provides a voice recognition service while the first application is operating It can be operated by multitasking.

The method according to an embodiment may be implemented in the form of a program command that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions to be recorded on the medium may be those specially designed and configured for the embodiments or may be available to those skilled in the art of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Magneto-optical media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions include machine language code such as those produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments. For example, it is to be understood that the techniques described may be performed in a different order than the described methods, and / or that components of the described systems, structures, devices, circuits, Lt; / RTI &gt; or equivalents, even if it is replaced or replaced.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (16)

A method for supporting multitasking of a speech recognition application in a communication terminal,
Operating the speech recognition application in an execution standby mode with the operation of the first application;
Receiving a predetermined awake up command of the speech recognition application and operating the speech recognition application in an execution mode;
Transmitting voice data recorded by a user through voice recognition application to a server; And
Receiving the execution result corresponding to the recording data from the server and operating the communication terminal
Lt; / RTI &gt;
Wherein the step of operating the speech recognition application in the execution standby mode together with the operation of the first application comprises:
Operating the first application while displaying the first application on a top layer of a display of the communication terminal; And
Operating the voice recognition application in a standby standby mode from a back-
A method for supporting multitasking of a speech recognition application in a communication terminal, comprising:
delete The method according to claim 1,
Wherein the step of operating the voice recognition application in the execution mode by receiving a predetermined awake up command of the voice recognition application comprises:
Receiving an awake up command of the speech recognition application;
Determining whether a wake-up command of the speech recognition application corresponds to a wake-up command of the predetermined speech recognition application; And
If it is determined that the awake up command of the speech recognition application corresponds to a wake up command of a predetermined speech recognition application,
The method comprising the steps of: receiving a voice recognition application;
The method of claim 3,
Wherein the step of operating the speech recognition application in an execution mode comprises:
Operating the voice recognition application in an execution mode on a back-ground while maintaining the operation of the first application so that the first application is displayed on a top layer of a display of the communication terminal
The method comprising the steps of: receiving a voice recognition application;
The method of claim 3,
The predetermined awake up command of the speech recognition application may include:
A predetermined speech recognition application execution instruction for executing the speech recognition application
A method for supporting multitasking of speech recognition applications in a communication terminal.
The method of claim 3,
The predetermined awake up command of the speech recognition application may include:
And is set to at least one of a voice received from the user or a call reception, a character reception, and a messenger reception in the standby mode of the voice recognition application
A method for supporting multitasking of speech recognition applications in a communication terminal.
The method according to claim 1,
Wherein the step of transmitting the voice data recorded by the user through the voice recognition application to the server comprises:
Transmitting the address book data stored in the communication terminal together to the server
The method comprising the steps of: receiving a voice recognition application;
The method according to claim 1,
Receiving the execution result corresponding to the recording data from the server and operating the communication terminal,
Executing at least one of an operation of calling a telephone, receiving a telephone call, sending a message, receiving a message, or receiving a messenger
The method comprising the steps of: receiving a voice recognition application;
9. The method of claim 8,
Displaying a message corresponding to the call origination, call reception, message origination, message reception or messenger reception operation on a window associated with the voice recognition application
The method comprising the steps of: providing a voice recognition application in a communication terminal;
10. The method of claim 9,
The step of displaying a message corresponding to the call origination, call reception, message origination, message reception or messenger reception operation on a window associated with the voice recognition application,
Overlapping a window associated with the speech recognition application with the first application in a semitransparent manner and displaying on the display of the communication terminal
The method comprising the steps of: receiving a voice recognition application;
11. The method of claim 10,
The step of overlapping the window associated with the speech recognition application with the first application translucently and displaying the overlap on the display of the communication terminal,
Adaptively adjusting the size of the window according to the length of the text data corresponding to the voice data and displaying the adjusted size;
The method comprising the steps of: receiving a voice recognition application;
The method according to claim 1,
Receiving the execution result corresponding to the recording data from the server and operating the communication terminal,
Measuring an ambient noise magnitude through a microphone of the communication terminal;
Comparing the ambient noise magnitude and the speaker volume magnitude of the communication terminal; And
Adjusting the speaker volume size based on the ambient noise magnitude
The method comprising the steps of: receiving a voice recognition application;
The method according to claim 1,
Receiving the execution result corresponding to the recording data from the server and operating the communication terminal,
Adaptively adjusting an output volume size of the speech recognition application and the first application
The method comprising the steps of: receiving a voice recognition application;
The method according to claim 1,
Wherein the step of operating the voice recognition application in the standby mode, together with the operation of the first application,
The screen of the communication terminal is turned off,
When the communication terminal is locked off,
Wherein the communication terminal is in an idle state,
A state in which the communication terminal receives a voice call; And
When the communication terminal receives a text message
Operating the speech recognition application in a standby mode even in at least one of
The method comprising the steps of: receiving a voice recognition application;
A computer-readable recording medium storing a program for executing the method of any one of claims 1 to 14.
A memory in which a speech recognition application is recorded; And
A processor for controlling execution of the speech recognition application;
Lt; / RTI &gt;
The processor comprising:
The voice recognition application is operated in the execution standby mode together with the operation of the first application,
Operating the speech recognition application in an execution mode by a predetermined awake up command of the speech recognition application,
Transmitting voice data recorded by a user through voice recognition application to a server,
Receiving an execution result corresponding to the recording data from the server to operate the communication terminal,
The execution standby mode includes:
The first application is operated while displaying the first application on a top layer of the display of the communication terminal, and the voice recognition application is operated in the back-
Communication terminal.

Images